Metadata-Version: 2.4
Name: precisionai-agristress-utils
Version: 1.0.0
Summary: Dataset utilities for AgriStress-500 — HuggingFace download, metadata lookup, and retrieval payload assembly for the PAI embedding evaluator.
Author-email: Precision AI <michael@precision.ai>
Maintainer-email: Precision AI <michael@precision.ai>
License:                                  Apache License
                                   Version 2.0, January 2004
                                http://www.apache.org/licenses/
        
           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
        
           1. Definitions.
        
              "License" shall mean the terms and conditions for use, reproduction,
              and distribution as defined by Sections 1 through 9 of this document.
        
              "Licensor" shall mean the copyright owner or entity authorized by
              the copyright owner that is granting the License.
        
              "Legal Entity" shall mean the union of the acting entity and all
              other entities that control, are controlled by, or are under common
              control with that entity. For the purposes of this definition,
              "control" means (i) the power, direct or indirect, to cause the
              direction or management of such entity, whether by contract or
              otherwise, or (ii) ownership of fifty percent (50%) or more of the
              outstanding shares, or (iii) beneficial ownership of such entity.
        
              "You" (or "Your") shall mean an individual or Legal Entity
              exercising permissions granted by this License.
        
              "Source" form shall mean the preferred form for making modifications,
              including but not limited to software source code, documentation
              source, and configuration files.
        
              "Object" form shall mean any form resulting from mechanical
              transformation or translation of a Source form, including but
              not limited to compiled object code, generated documentation,
              and conversions to other media types.
        
              "Work" shall mean the work of authorship made available under
              the License, as indicated by a copyright notice that is included in
              or attached to the work (an example is provided in the Appendix below).
        
              "Derivative Works" shall mean any work, whether in Source or Object
              form, that is based on (or derived from) the Work and for which the
              editorial revisions, annotations, elaborations, or other modifications
              represent, as a whole, an original work of authorship. For the purposes
              of this License, Derivative Works shall not include works that remain
              separable from, or merely link (or bind by name) to the interfaces of,
              the Work and Derivative Works thereof.
        
              "Contribution" shall mean, as submitted to the Licensor for inclusion
              in the Work by the copyright owner or by an individual or Legal Entity
              authorized to submit on behalf of the copyright owner. For the purposes
              of this definition, "submitted" means any form of electronic, verbal,
              or written communication sent to the Licensor or its representatives,
              including but not limited to communication on electronic mailing lists,
              source code control systems, and issue tracking systems that are managed
              by, or on behalf of, the Licensor for the purpose of discussing and
              improving the Work, but excluding communication that is conspicuously
              marked or designated in writing by the copyright owner as "Not a
              Contribution."
        
              "Contributor" shall mean Licensor and any Legal Entity on behalf of
              whom a Contribution has been received by the Licensor and incorporated
              within the Work.
        
           2. Grant of Copyright License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              copyright license to reproduce, prepare Derivative Works of,
              publicly display, publicly perform, sublicense, and distribute the
              Work and such Derivative Works in Source or Object form.
        
           3. Grant of Patent License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              (except as stated in this section) patent license to make, have made,
              use, offer to sell, sell, import, and otherwise transfer the Work,
              where such license applies only to those patent claims licensable
              by such Contributor that are necessarily infringed by their
              Contribution(s) alone or by combination of their Contribution(s)
              with the Work to which such Contribution(s) was submitted. If You
              institute patent litigation against any entity (including a
              cross-claim or counterclaim in a lawsuit) alleging that the Work
              or a Contribution incorporated within the Work constitutes direct
              or contributory patent infringement, then any patent licenses
              granted to You under this License for that Work shall terminate
              as of the date such litigation is filed.
        
           4. Redistribution. You may reproduce and distribute copies of the
              Work or Derivative Works thereof in any medium, with or without
              modifications, and in Source or Object form, provided that You
              meet the following conditions:
        
              (a) You must give any other recipients of the Work or Derivative
                  Works a copy of this License; and
        
              (b) You must cause any modified files to carry prominent notices
                  stating that You changed the files; and
        
              (c) You must retain, in the Source form of any Derivative Works
                  that You distribute, all copyright, patent, trademark, and
                  attribution notices from the Source form of the Work,
                  excluding those notices that do not pertain to any part of
                  the Derivative Works; and
        
              (d) If the Work includes a "NOTICE" text file as part of its
                  distribution, You must include a readable copy of the
                  attribution notices contained within such NOTICE file, in
                  at least one of the following places: within a NOTICE text
                  file distributed as part of the Derivative Works; within
                  the Source form or documentation, if provided along with the
                  Derivative Works; or, within a display generated by the
                  Derivative Works, if and wherever such third-party notices
                  normally appear. The contents of the NOTICE file are for
                  informational purposes only and do not modify the License.
                  You may add Your own attribution notices within Derivative
                  Works that You distribute, alongside or as an addendum to
                  the NOTICE text from the Work, provided that such additional
                  attribution notices cannot be construed as modifying the
                  License.
        
              You may add Your own license statement for Your modifications and
              may provide additional grant of rights to use, copy, modify, merge,
              publish, distribute, sublicense, and/or sell copies of the
              Contribution, either on behalf of the copyright owners or
              separately from the copyright owners, and You may only add
              Your own license statement for Your modifications.
        
           5. Submission of Contributions. Unless You explicitly state otherwise,
              any Contribution intentionally submitted for inclusion in the Work
              by You to the Licensor shall be under the terms and conditions of
              this License, without any additional terms or conditions.
              Notwithstanding the above, nothing herein shall supersede or modify
              the terms of any separate license agreement you may have executed
              with Licensor regarding such Contributions.
        
           6. Trademarks. This License does not grant permission to use the trade
              names, trademarks, service marks, or product names of the Licensor,
              except as required for reasonable and customary use in describing the
              origin of the Work and reproducing the content of the NOTICE file.
        
           7. Disclaimer of Warranty. Unless required by applicable law or
              agreed to in writing, Licensor provides the Work (and each
              Contributor provides its Contributions) on an "AS IS" BASIS,
              WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
              implied, including, without limitation, any warranties or conditions
              of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
              PARTICULAR PURPOSE. You are solely responsible for determining the
              appropriateness of using or reproducing the Work and assume any
              risks associated with Your exercise of permissions under this License.
        
           8. Limitation of Liability. In no event and under no legal theory,
              whether in tort (including negligence), contract, or otherwise,
              unless required by applicable law (such as deliberate and grossly
              negligent acts) or agreed to in writing, shall any Contributor be
              liable to You for damages, including any direct, indirect, special,
              incidental, or exemplary damages of any character arising as a
              result of this License or out of the use or inability to use the
              Work (including but not limited to damages for loss of goodwill,
              work stoppage, computer failure or malfunction, or all other
              commercial damages or losses), even if such Contributor has been
              advised of the possibility of such damages.
        
           9. Accepting Warranty or Additional Liability. While redistributing
              the Work or Derivative Works thereof, You may choose to offer,
              and charge a fee for, acceptance of support, warranty, indemnity,
              or other liability obligations and/or rights consistent with this
              License. However, in accepting such obligations, You may offer only
              conditions that are solely Your own responsibility, and not on
              behalf of any other Contributor, and only if You agree to indemnify,
              defend, and hold each Contributor harmless for any liability
              incurred by, or claims asserted against, such Contributor by reason
              of your accepting any such warranty or additional liability.
        
           END OF TERMS AND CONDITIONS
        
           Copyright 2025 Precision AI, Inc.
        
           Licensed under the Apache License, Version 2.0 (the "License");
           you may not use this file except in compliance with the License.
           You may obtain a copy of the License at
        
               http://www.apache.org/licenses/LICENSE-2.0
        
           Unless required by applicable law or agreed to in writing, software
           distributed under the License is distributed on an "AS IS" BASIS,
           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
           implied. See the License for the specific language governing
           permissions and limitations under the License.
        
Project-URL: Homepage, https://github.com/Precision-AI-Inc/agristress-utils
Project-URL: Repository, https://github.com/Precision-AI-Inc/agristress-utils
Project-URL: Issues, https://github.com/Precision-AI-Inc/agristress-utils/issues
Project-URL: Changelog, https://github.com/Precision-AI-Inc/agristress-utils/blob/main/CHANGELOG.md
Keywords: agriculture,computer-vision,dataset,embeddings,evaluation,machine-learning
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Image Recognition
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE.md
Requires-Dist: pydantic>=2.0
Requires-Dist: huggingface_hub>=0.23
Provides-Extra: test
Requires-Dist: pytest>=7.0; extra == "test"
Requires-Dist: pytest-cov>=5.0; extra == "test"
Provides-Extra: dev
Requires-Dist: pytest>=7.0; extra == "dev"
Requires-Dist: pytest-cov>=5.0; extra == "dev"
Requires-Dist: pre-commit>=3.7; extra == "dev"
Requires-Dist: pyright>=1.1; extra == "dev"
Dynamic: license-file

<p align="center">
  <img src="https://raw.githubusercontent.com/Precision-AI-Inc/agristress-utils/main/docs/assets/logo.png" alt="Precision AI Logo" width="120"/>
</p>

# PAI AgriStress Utils

Dataset utilities for AgriStress-500 — download the dataset from HuggingFace, look up image and instance metadata, and assemble ready-to-POST payloads for the [`agrieval`](https://github.com/Precision-AI-Inc/agrieval) embedding evaluator.

[![PyPI](https://img.shields.io/pypi/v/precisionai-agristress-utils.svg?include_prereleases)](https://pypi.org/project/precisionai-agristress-utils/)
[![Python](https://img.shields.io/pypi/pyversions/precisionai-agristress-utils.svg?include_prereleases)](https://pypi.org/project/precisionai-agristress-utils/)
[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/Precision-AI-Inc/agristress-utils/blob/main/LICENSE.md)

---

## Installation

```bash
python -m venv .venv && source .venv/bin/activate  # Windows: .venv\Scripts\activate

pip install precisionai-agristress-utils

# Full development (tests, pre-commit, type checking)
pip install -e ".[dev]"
```

---

## Quick start

```python
from precisionai.agristress.utils import AgriStressDataset, download_dataset

download_dataset("/path/to/agristress", repo_id="precisionaiinc/AgriStress-500")
ds = AgriStressDataset("/path/to/agristress")
```

See [`examples/`](https://github.com/Precision-AI-Inc/agristress-utils/blob/main/examples/) for complete walkthroughs of all three evaluator routes and dataset validation.

---

## Downloading the dataset

```python
from precisionai.agristress.utils import download_dataset

download_dataset("/path/to/agristress", repo_id="precisionaiinc/AgriStress-500")
```

Single-shot only — partial downloads are not supported. The `internal/` directory is always excluded. Returns the resolved local `Path`.

After downloading, the directory layout is:

```
/path/to/agristress/
  images/          # source images, one subdirectory per L2 cluster
  instances/       # instance crops, one subdirectory per annotated cluster
  image2image.json
  plant2image.json
  plant2plant.json
  README.md
```

Pass that directory directly to `AgriStressDataset`:

```python
ds = AgriStressDataset("/path/to/agristress")
```

---

## Enumeration and filtering

Before embedding images you need to know what IDs exist. All IDs are relative paths that match the dataset layout exactly (e.g. `"images/A1/pai-FvearqMK.png"`).

```python
# All clusters, images, and instances
clusters      = ds.list_clusters()                        # sorted list of L2 cluster names
all_images    = ds.list_image_ids()                       # all image paths
all_instances = ds.list_instance_ids()                    # all instance paths

# Narrow by cluster or label
a1_images     = ds.list_image_ids(cluster="A1")
soy_instances = ds.list_instance_ids(label="Crop | Soybean")

# Filter by cluster attributes — scalar or list values
drone_images  = ds.filter_images_by_attribute(camera_source="drone")
noon_drone    = ds.filter_images_by_attribute(camera_source="drone", time_period="noon")
soy_clusters  = ds.filter_images_by_attribute(plants="Crop | Soybean")
```

---

## Path resolution

Map relative IDs to absolute file paths so you can open them with your image loader:

```python
paths = ds.resolve_paths(ds.list_image_ids(cluster="A1"))
# {"images/A1/pai-FvearqMK.png": Path("/path/to/agristress/images/A1/pai-FvearqMK.png"), ...}

from PIL import Image
for abs_path in paths.values():
    img = Image.open(abs_path)
    # … run embedding model
```

Both image and instance IDs are accepted. The returned paths are resolved but not checked for existence.

---

## Embedding utilities

The `agrieval` evaluator requires every vector to be **L2-normalized** (‖v‖₂ = 1.0 ± 1e-3). Use these utilities to normalize and validate before building payloads:

```python
from precisionai.agristress.utils import normalize_embeddings, validate_embeddings

# Normalize raw model output
raw = {"images/A1/pai-FvearqMK.png": model.encode(...)}  # unnormalized
normed = normalize_embeddings(raw)                        # returns new dict, does not mutate

# Validate before posting (raises ValueError if any vector deviates)
validate_embeddings(normed)
```

`normalize_embeddings` raises `ValueError` for zero vectors. `validate_embeddings` raises `ValueError` with the offending path and its actual norm if any vector fails the check.

---

## Metadata lookups

IDs are relative paths matching the dataset layout (e.g. `"images/A1/pai-FvearqMK.png"`).

### Image metadata

```python
records = ds.image_metadata([
    "images/A1/pai-FvearqMK.png",
    "images/A1/pai-XYZ123.png",
])
for r in records:
    print(r.image_id, r.cluster, r.attributes.plants, r.instances)
```

Optionally attach embeddings. Embeddings are **all-or-nothing** — every requested ID must have an entry in the dict, or `ValueError` is raised:

```python
embeddings = {
    "images/A1/pai-FvearqMK.png": [...],
    "images/A1/pai-XYZ123.png":   [...],
}
records = ds.image_metadata(list(embeddings), embeddings=embeddings)
print(records[0].embedding)   # [...] populated
```

### Instance metadata

```python
records = ds.instance_metadata([
    "instances/A1/pai-FvearqMK-1.png",
])
for r in records:
    print(r.instance_id, r.label, r.parent_image)
```

---

## Retrieval payload builders

Assemble the exact request body expected by `agrieval`. All embedding vectors must be **L2-normalized** flat `list[float]`.

| Method | Evaluator endpoint |
|---|---|
| `build_i2i_payload(embeddings)` | `POST /v1/embeddings/evaluate/image2image` |
| `build_p2i_payload(embeddings)` | `POST /v1/embeddings/evaluate/plant2image` |
| `build_p2p_payload(embeddings)` | `POST /v1/embeddings/evaluate/plant2plant` |

```python
# Image → Image
i2i = ds.build_i2i_payload(image_embeddings, k_values=[5, 10, 20])

# Plant → Image  (embeddings must include BOTH image and instance paths)
p2i = ds.build_p2i_payload(combined_embeddings)

# Plant → Plant  (instance paths only)
p2p = ds.build_p2p_payload(instance_embeddings, sample_pairs=None)
```

Embedding keys not present in the dataset manifests are ignored. Clusters or instance groups with no matching embedding are dropped from the payload automatically.

---

## Project layout

```
precisionai/agristress/utils/
  dataset/
    download.py      # HuggingFace single-shot download
    loader.py        # AgriStressDataset — metadata lookups + payload builders
  schemas/
    dataset.py       # ImageRecord, InstanceRecord, ImageAttributes  (Pydantic)
    retrieval.py     # I2IPayload, P2IPayload, P2PPayload  (TypedDicts)
docs/                # Sphinx (HTML + LaTeX/PDF)
tests/               # Mirrors package structure
examples/            # Standalone runnable scripts
```

---

## Development

See [CONTRIBUTING.md](https://github.com/Precision-AI-Inc/agristress-utils/blob/main/CONTRIBUTING.md) for setup, branching, and PR guidelines, and [CODE_OF_CONDUCT.md](https://github.com/Precision-AI-Inc/agristress-utils/blob/main/CODE_OF_CONDUCT.md) for community expectations. [CLAUDE.md](https://github.com/Precision-AI-Inc/agristress-utils/blob/main/CLAUDE.md) documents the code style and conventions enforced in this repo.

```bash
# Run all tests with coverage report
python -m pytest

# Run a specific file
pytest tests/test_loader.py

# Run pre-commit hooks manually
pre-commit run --all-files
```

---

## License

Licensed under the Apache License, Version 2.0. See [LICENSE.md](https://github.com/Precision-AI-Inc/agristress-utils/blob/main/LICENSE.md).

See [CHANGELOG.md](https://github.com/Precision-AI-Inc/agristress-utils/blob/main/CHANGELOG.md) for release history.
